{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z3GDLMSLBNJPTYOEHJTMEM6OR3","short_pith_number":"pith:Z3GDLMSL","canonical_record":{"source":{"id":"2505.07070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T17:44:14Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"b4fcf3c360d0d38809da7c657ba9cdb503b321a78a947d9212728e6e0cb5be5e","abstract_canon_sha256":"d17e768028433e822880754f1df281143f0e4aa6bd304468fd16f308297f394f"},"schema_version":"1.0"},"canonical_sha256":"cecc35b24b0b52f9e1c43a66c233ce8ece06d54db6da6221a5ebab0582f1a997","source":{"kind":"arxiv","id":"2505.07070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07070","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07070v1","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07070","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"Z3GDLMSLBNJP","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"Z3GDLMSLBNJPTYOE","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"Z3GDLMSL","created_at":"2026-07-05T11:01:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z3GDLMSLBNJPTYOEHJTMEM6OR3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T17:44:14Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"b4fcf3c360d0d38809da7c657ba9cdb503b321a78a947d9212728e6e0cb5be5e","abstract_canon_sha256":"d17e768028433e822880754f1df281143f0e4aa6bd304468fd16f308297f394f"},"schema_version":"1.0"},"canonical_sha256":"cecc35b24b0b52f9e1c43a66c233ce8ece06d54db6da6221a5ebab0582f1a997","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:42.254614Z","signature_b64":"N0fUCBu12PDY7o1SQHNfLeqkKZNzud4EE0R0hHoG0HJ997ghPKEZe+eKeH0fFORo5PXvPSTVMcEI4CkN2ThlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cecc35b24b0b52f9e1c43a66c233ce8ece06d54db6da6221a5ebab0582f1a997","last_reissued_at":"2026-07-05T11:01:42.254152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:42.254152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07070","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4E5zWTj0KIaR8iHfIj1oSyWUYlqohGB6NRoxGP5mkqb3zR3gjOI50CSsSHKvlku7M1rv8FIIm0k4SmiAEMBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:43:31.219095Z"},"content_sha256":"534a516214bb76bccf2b660393b74fa1af3843d2fcb506fdefca9727f15f119a","schema_version":"1.0","event_id":"sha256:534a516214bb76bccf2b660393b74fa1af3843d2fcb506fdefca9727f15f119a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z3GDLMSLBNJPTYOEHJTMEM6OR3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Matthieu Wyart","submitted_at":"2025-05-11T17:44:14Z","abstract_excerpt":"How do neural language models acquire a language's structure when trained for next-token prediction? We address this question by deriving theoretical scaling laws for neural network performance on synthetic datasets generated by the Random Hierarchy Model (RHM) -- an ensemble of probabilistic context-free grammars designed to capture the hierarchical structure of natural language while remaining analytically tractable. Previously, we developed a theory of representation learning based on data correlations that explains how deep learning models capture the hierarchical structure of the data seq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07070","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.07070/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sL9xlbAvffP8yLkT1bnsZSOdNx4JE1lz64mLH1d2G5tTD88cYYi3d/2L0Oo9aZSxgjj9wloyuSSy4xBI4mECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:43:31.219498Z"},"content_sha256":"6047215bde68d698c91f7c681bd086211ce4de1455282ab802278c2d7fd89a94","schema_version":"1.0","event_id":"sha256:6047215bde68d698c91f7c681bd086211ce4de1455282ab802278c2d7fd89a94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3GDLMSLBNJPTYOEHJTMEM6OR3/bundle.json","state_url":"https://pith.science/pith/Z3GDLMSLBNJPTYOEHJTMEM6OR3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3GDLMSLBNJPTYOEHJTMEM6OR3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T05:43:31Z","links":{"resolver":"https://pith.science/pith/Z3GDLMSLBNJPTYOEHJTMEM6OR3","bundle":"https://pith.science/pith/Z3GDLMSLBNJPTYOEHJTMEM6OR3/bundle.json","state":"https://pith.science/pith/Z3GDLMSLBNJPTYOEHJTMEM6OR3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3GDLMSLBNJPTYOEHJTMEM6OR3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z3GDLMSLBNJPTYOEHJTMEM6OR3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d17e768028433e822880754f1df281143f0e4aa6bd304468fd16f308297f394f","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T17:44:14Z","title_canon_sha256":"b4fcf3c360d0d38809da7c657ba9cdb503b321a78a947d9212728e6e0cb5be5e"},"schema_version":"1.0","source":{"id":"2505.07070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07070","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07070v1","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07070","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"Z3GDLMSLBNJP","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"Z3GDLMSLBNJPTYOE","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"Z3GDLMSL","created_at":"2026-07-05T11:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:6047215bde68d698c91f7c681bd086211ce4de1455282ab802278c2d7fd89a94","target":"graph","created_at":"2026-07-05T11:01:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.07070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How do neural language models acquire a language's structure when trained for next-token prediction? We address this question by deriving theoretical scaling laws for neural network performance on synthetic datasets generated by the Random Hierarchy Model (RHM) -- an ensemble of probabilistic context-free grammars designed to capture the hierarchical structure of natural language while remaining analytically tractable. Previously, we developed a theory of representation learning based on data correlations that explains how deep learning models capture the hierarchical structure of the data seq","authors_text":"Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Matthieu Wyart","cross_cats":["cond-mat.dis-nn","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T17:44:14Z","title":"Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07070","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:534a516214bb76bccf2b660393b74fa1af3843d2fcb506fdefca9727f15f119a","target":"record","created_at":"2026-07-05T11:01:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d17e768028433e822880754f1df281143f0e4aa6bd304468fd16f308297f394f","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T17:44:14Z","title_canon_sha256":"b4fcf3c360d0d38809da7c657ba9cdb503b321a78a947d9212728e6e0cb5be5e"},"schema_version":"1.0","source":{"id":"2505.07070","kind":"arxiv","version":1}},"canonical_sha256":"cecc35b24b0b52f9e1c43a66c233ce8ece06d54db6da6221a5ebab0582f1a997","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cecc35b24b0b52f9e1c43a66c233ce8ece06d54db6da6221a5ebab0582f1a997","first_computed_at":"2026-07-05T11:01:42.254152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:42.254152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N0fUCBu12PDY7o1SQHNfLeqkKZNzud4EE0R0hHoG0HJ997ghPKEZe+eKeH0fFORo5PXvPSTVMcEI4CkN2ThlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:42.254614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:534a516214bb76bccf2b660393b74fa1af3843d2fcb506fdefca9727f15f119a","sha256:6047215bde68d698c91f7c681bd086211ce4de1455282ab802278c2d7fd89a94"],"state_sha256":"08799c1dd029ed9a895b1f953b54202568bbda5bb233ca8c2b0d5c9c6cf244a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oVWaUnRcHmuC1fTTc9G+aSceNL1/MXmRH6VSphzW+bl97KEaFxfh1z6VBvOfqKC/45N2W2eT/2c+de/ZoPy3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:43:31.221754Z","bundle_sha256":"ae86fc6ad96650a003456023bc4512e279c41485a4cca3833a0568ab18f1629a"}}